
import pandas as pd
import numpy as np
import seaborn as sns
import plotly.express as px


df = pd.read_csv("dataset.csv")

df


df.head()


df.shape

(112634, 17)


df.tail()


df.columns

Index(['VIN (1-10)', 'County', 'City', 'State', 'Postal Code', 'Model Year',
       'Make', 'Model', 'Electric Vehicle Type',
       'Clean Alternative Fuel Vehicle (CAFV) Eligibility', 'Electric Range',
       'Base MSRP', 'Legislative District', 'DOL Vehicle ID',
       'Vehicle Location', 'Electric Utility', '2020 Census Tract'],
      dtype='object')


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 112634 entries, 0 to 112633
Data columns (total 17 columns):
 #   Column                                             Non-Null Count   Dtype  
---  ------                                             --------------   -----  
 0   VIN (1-10)                                         112634 non-null  object 
 1   County                                             112634 non-null  object 
 2   City                                               112634 non-null  object 
 3   State                                              112634 non-null  object 
 4   Postal Code                                        112634 non-null  int64  
 5   Model Year                                         112634 non-null  int64  
 6   Make                                               112634 non-null  object 
 7   Model                                              112614 non-null  object 
 8   Electric Vehicle Type                              112634 non-null  object 
 9   Clean Alternative Fuel Vehicle (CAFV) Eligibility  112634 non-null  object 
 10  Electric Range                                     112634 non-null  int64  
 11  Base MSRP                                          112634 non-null  int64  
 12  Legislative District                               112348 non-null  float64
 13  DOL Vehicle ID                                     112634 non-null  int64  
 14  Vehicle Location                                   112610 non-null  object 
 15  Electric Utility                                   112191 non-null  object 
 16  2020 Census Tract                                  112634 non-null  int64  
dtypes: float64(1), int64(6), object(10)
memory usage: 14.6+ MB


df.nunique().sort_values()

Electric Vehicle Type                                     2
Clean Alternative Fuel Vehicle (CAFV) Eligibility         3
Model Year                                               20
Base MSRP                                                30
Make                                                     34
State                                                    45
Legislative District                                     49
Electric Utility                                         73
Electric Range                                          101
Model                                                   114
County                                                  165
City                                                    629
Vehicle Location                                        758
Postal Code                                             773
2020 Census Tract                                      2026
VIN (1-10)                                             7548
DOL Vehicle ID                                       112634
dtype: int64


df.describe().T


df.isnull().sum()

VIN (1-10)                                             0
County                                                 0
City                                                   0
State                                                  0
Postal Code                                            0
Model Year                                             0
Make                                                   0
Model                                                 20
Electric Vehicle Type                                  0
Clean Alternative Fuel Vehicle (CAFV) Eligibility      0
Electric Range                                         0
Base MSRP                                              0
Legislative District                                 286
DOL Vehicle ID                                         0
Vehicle Location                                      24
Electric Utility                                     443
2020 Census Tract                                      0
dtype: int64


from pandas_profiling import ProfileReport


profile = ProfileReport(df, title="Housing Price Dataset")


profile

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]


df.replace("",np.nan)


df=df.dropna(axis='index',how='any')
df


df.isna().sum()

VIN (1-10)                                           0
County                                               0
City                                                 0
State                                                0
Postal Code                                          0
Model Year                                           0
Make                                                 0
Model                                                0
Electric Vehicle Type                                0
Clean Alternative Fuel Vehicle (CAFV) Eligibility    0
Electric Range                                       0
Base MSRP                                            0
Legislative District                                 0
DOL Vehicle ID                                       0
Vehicle Location                                     0
Electric Utility                                     0
2020 Census Tract                                    0
dtype: int64


df=df.drop_duplicates()

df


from pandas_profiling import ProfileReport


profile = ProfileReport(df, title="ELECTRIC VEHICLE DATASET")


profile

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]


corr=df.corr()
sns.heatmap(corr,annot=True)

<AxesSubplot:>


b = px.violin(t,x="Electric Range")
b.show()


t=df.groupby('Make').count().reset_index()


a = px.bar(t,x='Make',y='VIN (1-10)',color="Make",title="Count of Electric Vehiclesmade by each Company")


a.show()


t1=df.groupby('County').count().reset_index()


a = px.bar(t1,x='County',y='VIN (1-10)',color="County",title="Number of Cars in Each Country")
a.show()


Models = df.groupby('Model').count().sort_values(by='City',ascending=False)['City'].index
values = df.groupby('Model').count().sort_values(by='City',ascending=False)['City'].values


t2 = px.bar(x=list(Models)[:10],y=values[:10])

t2.show()


fig = px.scatter_matrix(df,
    dimensions=["County","Model Year","Make","Electric Range"],
    color="Make")
fig.show()


Vehicle_type = list(df.groupby('Electric Vehicle Type').count()['County'].index)
values = df.groupby('Electric Vehicle Type').count()['County'].values


fig1 = px.pie(names=Vehicle_type,values=values,height=400)
fig1.show()


states = list(df.groupby('State').count().sort_values(by='City',ascending=False)['City'].index)
values = df.groupby('State').count().sort_values(by='City',ascending=False)['City'].values


data = pd.DataFrame(df.groupby('State').count().sort_values(by='City',ascending=False)['City'])
data = data.reset_index()
data.columns = ['State','Count']


fig = px.choropleth(data,
                    locations='State', 
                    locationmode="USA-states", 
                    color='Count',
                    color_continuous_scale="greens", 
                    scope="usa")

fig.show()


df1 = df[['Model', 'Model Year']]


df['Model'].unique()

array(['LEAF', 'BOLT EV', 'FUSION', 'MODEL 3', 'SOUL', 'Q5 E', 'MODEL X',
       'VOLT', 'X5', '530E', 'TAYCAN', 'X3', 'A3', 'SOUL EV', 'C-MAX',
       '500', 'MODEL S', 'F-150', 'CT6', 'I3', 'MODEL Y', 'NIRO',
       'OUTLANDER', 'PACIFICA', 'R1T', 'CLARITY', 'KONA ELECTRIC', 'XC40',
       'ID.4', 'PRIUS PLUG-IN', 'MUSTANG MACH-E', 'EQB-CLASS',
       'RAV4 PRIME', 'E-GOLF', 'PRIUS PRIME', 'C40', 'SORENTO', 'XC60',
       'CAYENNE', 'WRANGLER', 'COUNTRYMAN', 'S60', 'EV6',
       'FORTWO ELECTRIC DRIVE', 'GRAND CHEROKEE', '330E', 'CROSSTREK',
       'IONIQ 5', 'IONIQ', 'E-TRON', 'ROADSTER', 'KONA', 'XC90', 'SPARK',
       'PS2', 'A7', 'HARDTOP', 'ESCAPE', 'LUCID AIR', 'E-TRON SPORTBACK',
       'Q5', 'RAV4', 'AVIATOR', 'E-TRON GT', 'EDV', 'IX', 'FORTWO',
       'I-PACE', 'SANTA FE', 'B-CLASS', 'KARMA', 'I4', 'OPTIMA',
       'GLC-CLASS', 'Q4', 'SONATA', 'EQ FORTWO', 'FOCUS',
       'RANGE ROVER SPORT', 'TRANSIT', 'PANAMERA', 'I8', 'BOLT EUV',
       'CORSAIR', 'ELR', 'GLE-CLASS', 'V60', 'EQS-CLASS SEDAN', 'R1S',
       'I-MIEV', 'NX', '740E', 'SPORTAGE', 'C-CLASS', 'S-CLASS', 'CITY',
       'S90', 'TUCSON', 'GV60', 'EQS-CLASS SUV', 'A8 E', 'RANGE ROVER',
       'RS E-TRON GT', 'RANGER', 'BENTAYGA', '745E',
       'TRANSIT CONNECT ELECTRIC', 'ACCORD', 'S-10 PICKUP', 'SOLTERRA',
       'G80', '918', 'FLYING SPUR', '745LE'], dtype=object)


t1=df1.groupby('Model Year').count().reset_index()
t1


df2=pd.crosstab(df1['Model'],[df1['Model Year']],rownames=["Model"],colnames=['Model Year'])


df2.fillna(0, inplace=True)
df2.sort_values(list(df2.columns),inplace=True)
df2 = df2.sort_index()

df2


df2.iloc[:, 0:-1] = df2.iloc[:, 0:-1].cumsum()


df2.head()


top_prem_clubs = set()

for index, row in df2.iterrows():
    top_prem_clubs |= set(row[row > 0].sort_values(ascending=False).head(6).index)

df2 = df2[top_prem_clubs]


import bar_chart_race as bcr


bcr.bar_chart_race(df = df2, 
                   n_bars = 6, 
                   sort='desc',
                   title='Premier League Clubs Points Since 1992',
                   filename = 'hack.mp4')

c:\users\gsind\appdata\local\programs\python\python37\lib\site-packages\bar_chart_race\_make_chart.py:286: UserWarning:

FixedFormatter should only be used together with FixedLocator

c:\users\gsind\appdata\local\programs\python\python37\lib\site-packages\bar_chart_race\_make_chart.py:287: UserWarning:

FixedFormatter should only be used together with FixedLocator

MovieWriter imagemagick unavailable; using Pillow instead.

	VIN (1-10)	County	City	State	Postal Code	Model Year	Make	Model	Electric Vehicle Type	Clean Alternative Fuel Vehicle (CAFV) Eligibility	Electric Range	Base MSRP	Legislative District	DOL Vehicle ID	Vehicle Location	Electric Utility	2020 Census Tract
0	JTMEB3FV6N	Monroe	Key West	FL	33040	2022	TOYOTA	RAV4 PRIME	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	42	0	NaN	198968248	POINT (-81.80023 24.5545)	NaN	12087972100
1	1G1RD6E45D	Clark	Laughlin	NV	89029	2013	CHEVROLET	VOLT	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	38	0	NaN	5204412	POINT (-114.57245 35.16815)	NaN	32003005702
2	JN1AZ0CP8B	Yakima	Yakima	WA	98901	2011	NISSAN	LEAF	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	73	0	15.0	218972519	POINT (-120.50721 46.60448)	PACIFICORP	53077001602
3	1G1FW6S08H	Skagit	Concrete	WA	98237	2017	CHEVROLET	BOLT EV	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	238	0	39.0	186750406	POINT (-121.7515 48.53892)	PUGET SOUND ENERGY INC	53057951101
4	3FA6P0SU1K	Snohomish	Everett	WA	98201	2019	FORD	FUSION	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	26	0	38.0	2006714	POINT (-122.20596 47.97659)	PUGET SOUND ENERGY INC	53061041500
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
112629	7SAYGDEF2N	King	Duvall	WA	98019	2022	TESLA	MODEL Y	Battery Electric Vehicle (BEV)	Eligibility unknown as battery range has not b...	0	0	45.0	217955265	POINT (-121.98609 47.74068)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032401
112630	1N4BZ1CP7K	San Juan	Friday Harbor	WA	98250	2019	NISSAN	LEAF	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	150	0	40.0	103663227	POINT (-123.01648 48.53448)	BONNEVILLE POWER ADMINISTRATION\|\|ORCAS POWER &...	53055960301
112631	1FMCU0KZ4N	King	Vashon	WA	98070	2022	FORD	ESCAPE	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	38	0	34.0	193878387	POINT (-122.4573 47.44929)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033027702
112632	KNDCD3LD4J	King	Covington	WA	98042	2018	KIA	NIRO	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	26	0	47.0	125039043	POINT (-122.09124 47.33778)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032007
112633	YV4BR0CL8N	King	Covington	WA	98042	2022	VOLVO	XC90	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	18	0	47.0	194673692	POINT (-122.09124 47.33778)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032005

	VIN (1-10)	County	City	State	Postal Code	Model Year	Make	Model	Electric Vehicle Type	Clean Alternative Fuel Vehicle (CAFV) Eligibility	Electric Range	Legislative District	DOL Vehicle ID	Vehicle Location	Electric Utility	2020 Census Tract
0	JTMEB3FV6N	Monroe	Key West	FL	33040	2022	TOYOTA	RAV4 PRIME	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	42	NaN	198968248	POINT (-81.80023 24.5545)	NaN	12087972100
1	1G1RD6E45D	Clark	Laughlin	NV	89029	2013	CHEVROLET	VOLT	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	38	NaN	5204412	POINT (-114.57245 35.16815)	NaN	32003005702
2	JN1AZ0CP8B	Yakima	Yakima	WA	98901	2011	NISSAN	LEAF	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	73	15.0	218972519	POINT (-120.50721 46.60448)	PACIFICORP	53077001602
3	1G1FW6S08H	Skagit	Concrete	WA	98237	2017	CHEVROLET	BOLT EV	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	238	39.0	186750406	POINT (-121.7515 48.53892)	PUGET SOUND ENERGY INC	53057951101
4	3FA6P0SU1K	Snohomish	Everett	WA	98201	2019	FORD	FUSION	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	26	38.0	2006714	POINT (-122.20596 47.97659)	PUGET SOUND ENERGY INC	53061041500

	VIN (1-10)	County	City	State	Postal Code	Model Year	Make	Model	Electric Vehicle Type	Clean Alternative Fuel Vehicle (CAFV) Eligibility	Electric Range	Legislative District	DOL Vehicle ID	Vehicle Location	Electric Utility	2020 Census Tract
112629	7SAYGDEF2N	King	Duvall	WA	98019	2022	TESLA	MODEL Y	Battery Electric Vehicle (BEV)	Eligibility unknown as battery range has not b...	0	45.0	217955265	POINT (-121.98609 47.74068)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032401
112630	1N4BZ1CP7K	San Juan	Friday Harbor	WA	98250	2019	NISSAN	LEAF	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	150	40.0	103663227	POINT (-123.01648 48.53448)	BONNEVILLE POWER ADMINISTRATION\|\|ORCAS POWER &...	53055960301
112631	1FMCU0KZ4N	King	Vashon	WA	98070	2022	FORD	ESCAPE	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	38	34.0	193878387	POINT (-122.4573 47.44929)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033027702
112632	KNDCD3LD4J	King	Covington	WA	98042	2018	KIA	NIRO	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	26	47.0	125039043	POINT (-122.09124 47.33778)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032007
112633	YV4BR0CL8N	King	Covington	WA	98042	2022	VOLVO	XC90	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	18	47.0	194673692	POINT (-122.09124 47.33778)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032005

	count	mean	std	min	25%	50%	75%	max
Postal Code	112634.0	9.815623e+04	2.648733e+03	1.730000e+03	9.805200e+04	9.811900e+04	9.837000e+04	9.970100e+04
Model Year	112634.0	2.019003e+03	2.892364e+00	1.997000e+03	2.017000e+03	2.020000e+03	2.022000e+03	2.023000e+03
Electric Range	112634.0	8.781299e+01	1.023342e+02	0.000000e+00	0.000000e+00	3.200000e+01	2.080000e+02	3.370000e+02
Base MSRP	112634.0	1.793440e+03	1.078375e+04	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	8.450000e+05
Legislative District	112348.0	2.980560e+01	1.470055e+01	1.000000e+00	1.800000e+01	3.400000e+01	4.300000e+01	4.900000e+01
DOL Vehicle ID	112634.0	1.994567e+08	9.398427e+07	4.777000e+03	1.484142e+08	1.923896e+08	2.191899e+08	4.792548e+08
2020 Census Tract	112634.0	5.296650e+10	1.699104e+09	1.101001e+09	5.303301e+10	5.303303e+10	5.305307e+10	5.603300e+10

	VIN (1-10)	County	City	State	Postal Code	Model Year	Make	Model	Electric Vehicle Type	Clean Alternative Fuel Vehicle (CAFV) Eligibility	Electric Range	Base MSRP	Legislative District	DOL Vehicle ID	Vehicle Location	Electric Utility	2020 Census Tract
0	JTMEB3FV6N	Monroe	Key West	FL	33040	2022	TOYOTA	RAV4 PRIME	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	42	0	NaN	198968248	POINT (-81.80023 24.5545)	NaN	12087972100
1	1G1RD6E45D	Clark	Laughlin	NV	89029	2013	CHEVROLET	VOLT	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	38	0	NaN	5204412	POINT (-114.57245 35.16815)	NaN	32003005702
2	JN1AZ0CP8B	Yakima	Yakima	WA	98901	2011	NISSAN	LEAF	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	73	0	15.0	218972519	POINT (-120.50721 46.60448)	PACIFICORP	53077001602
3	1G1FW6S08H	Skagit	Concrete	WA	98237	2017	CHEVROLET	BOLT EV	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	238	0	39.0	186750406	POINT (-121.7515 48.53892)	PUGET SOUND ENERGY INC	53057951101
4	3FA6P0SU1K	Snohomish	Everett	WA	98201	2019	FORD	FUSION	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	26	0	38.0	2006714	POINT (-122.20596 47.97659)	PUGET SOUND ENERGY INC	53061041500
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
112629	7SAYGDEF2N	King	Duvall	WA	98019	2022	TESLA	MODEL Y	Battery Electric Vehicle (BEV)	Eligibility unknown as battery range has not b...	0	0	45.0	217955265	POINT (-121.98609 47.74068)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032401
112630	1N4BZ1CP7K	San Juan	Friday Harbor	WA	98250	2019	NISSAN	LEAF	Battery Electric Vehicle (BEV)	Clean Alternative Fuel Vehicle Eligible	150	0	40.0	103663227	POINT (-123.01648 48.53448)	BONNEVILLE POWER ADMINISTRATION\|\|ORCAS POWER &...	53055960301
112631	1FMCU0KZ4N	King	Vashon	WA	98070	2022	FORD	ESCAPE	Plug-in Hybrid Electric Vehicle (PHEV)	Clean Alternative Fuel Vehicle Eligible	38	0	34.0	193878387	POINT (-122.4573 47.44929)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033027702
112632	KNDCD3LD4J	King	Covington	WA	98042	2018	KIA	NIRO	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	26	0	47.0	125039043	POINT (-122.09124 47.33778)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032007
112633	YV4BR0CL8N	King	Covington	WA	98042	2022	VOLVO	XC90	Plug-in Hybrid Electric Vehicle (PHEV)	Not eligible due to low battery range	18	0	47.0	194673692	POINT (-122.09124 47.33778)	PUGET SOUND ENERGY INC\|\|CITY OF TACOMA - (WA)	53033032005

IMPORT ALL THE LIBRARIES¶

READ THE DATASET¶

information about the columns in dataset¶

check number of null values¶

Data visualization¶

UNIVARIATE ANALYSIS¶

BI-VARIATE ANALYSIS¶

Observation : From the Above Figure We can say That TESLa Company is Having more number of elctric vehicles¶

OBSERVATION - King Country has more Electric Vehicles¶

OBSERVATION -- MODEL3 has manufactured more Electric Cars¶

OBSERVATION --Plug-in hybrid Electric Vehicles are more than Battery Electric Vehicles¶

TASK-2¶

Observation From the above Choropleth we can say that all of the companies are in WA state¶

TASK 3¶

	Model Year	Model
0	1997	1
1	1998	1
2	1999	3
3	2000	10
4	2002	2
5	2008	23
6	2010	24
7	2011	835
8	2012	1695
9	2013	4669
10	2014	3665
11	2015	4918
12	2016	5709
13	2017	8598
14	2018	14190
15	2019	10216
16	2020	10998
17	2021	18277
18	2022	26455
19	2023	1863

Model Year	1997	1998	1999	2000	2002	2008	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Model
330E	0	0	0	0	0	0	0	0	0	0	0	0	10	95	76	0	0	64	54	0
500	0	0	0	0	0	0	0	0	0	106	97	242	147	166	53	9	0	0	0	0
530E	0	0	0	0	0	0	0	0	0	0	0	0	0	0	202	75	3	18	25	0
740E	0	0	0	0	0	0	0	0	0	0	0	0	0	7	18	4	0	0	0	0
745E	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	7	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
X3	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	80	212	0	0
X5	0	0	0	0	0	0	0	0	0	0	0	0	169	175	181	0	0	300	577	0
XC40	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	245	249	1
XC60	0	0	0	0	0	0	0	0	0	0	0	0	0	0	125	107	87	143	235	0
XC90	0	0	0	0	0	0	0	0	0	0	0	0	112	115	82	70	59	155	224	0